There is, I think, something ethereal about i —the square root of minus one. I remember first hearing about it at school. It seemed an odd beast at that time—an intruder hovering on the edge of reality.

Usually familiarity dulls this sense of the bizarre, but in the case of i it was the reverse: over the years the sense of its surreal nature intensified. It seemed that it was impossible to write mathematics that described the real world in …

I and i

Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

From the Publisher: 
The accessible presentation of this book gives both a general view of the entire computer vision enterprise and also offers sufficient detail to be able to build useful applications. Users learn techniques that have proven to be useful by first-hand experience and a wide range of mathematical methods. A CD-ROM with every copy of the text contains source code for programming practice, color images, and illustrative movies. Comprehensive and up-to-date, this book includes essential topics that either reflect practical significance or are of theoretical importance. Topics are discussed in substantial and increasing depth. Application surveys describe numerous important application areas such as image based rendering and digital libraries. Many important algorithms broken down and illustrated in pseudo code. Appropriate for use by engineers as a comprehensive reference to the computer vision enterprise.

Computer vision : a modern approach = 计算机视觉 : 一种现代的方法

This paper investigates long-term tracking of unknown objects in a video stream. The object is defined by its location and extent in a single frame. In every frame that follows, the task is to determine the object's location and extent or indicate that the object is not present. We propose a novel tracking framework (TLD) that explicitly decomposes the long-term tracking task into tracking, learning, and detection. The tracker follows the object from frame to frame. The detector localizes all appearances that have been observed so far and corrects the tracker if necessary. The learning estimates the detector's errors and updates it to avoid these errors in the future. We study how to identify the detector's errors and learn from them. We develop a novel learning method (P-N learning) which estimates the errors by a pair of “experts”: (1) P-expert estimates missed detections, and (2) N-expert estimates false alarms. The learning process is modeled as a discrete dynamical system and the conditions under which the learning guarantees improvement are found. We describe our real-time implementation of the TLD framework and the P-N learning. We carry out an extensive quantitative evaluation which shows a significant improvement over state-of-the-art approaches.

Tracking-Learning-Detection

This paper proposes a pervasive retail architecture based on a free human gaze estimation system. The main aim of the paper is to investigate the possibility to automatically understand the behavior of the persons looking at a shop window: this is done by a gaze estimation technique that uses a RGB-D device in order to extract head pose information from which a fast geometric technique then evaluates the focus of attention of the persons in the scene (even more persons at the same time). The main contribution concerns with the application into this challenging research field of a gaze estimation working without any initial calibration and, in spite of this, able to properly deal with completely unaware persons moving in unconstrained environments. Preliminary experiments were conducted in our lab in order to quantitative validate the accuracy of the gaze estimation on different benchmarks of persons. Then the qualitative evaluation of the effectiveness of the proposed architecture was conducted in a real shop window demonstrating the ability to deal with real challenging environmental conditions.

Video Analytics for Audience Measurement

Detection and tracking algorithms generates useful information in the form of trajectories from which the behaviors and the interactions of moving objects can be inferred through the analysis of spatio-temporal features. Interactions occur either between a dynamic and a static object, or between multiple dynamic objects. This chapter presents an interaction modeling framework formulated as a state sequence estimation problem using time-series analysis. Bayesian network-based methods and their variants are studied for the analysis of interactions in videos. Moreover, techniques such as Coupled Hidden Markov Model are also discussed for more complex interactions, such as those between multiple dynamic objects. Finally, the interaction modeling is demonstrated on real surveillance and sport sequences.

Recognizing Interactions in Video

Our voice encodes a uniquely identiﬁable pattern which can be used to infer private attributes, such as gender or identity, that an individual might wish not to reveal when using a speech recognition service. To prevent attribute inference attacks alongside speech recognition tasks, we present a generative adversarial network, GenGAN, that synthesises voices that conceal the gender or identity of a speaker. The proposed network includes a generator with a U-Net architecture that learns to fool a discriminator. We condition the generator only on gender information and use an adversarial loss between signal distortion and privacy preservation. We show that GenGAN improves the trade-off between privacy and utility compared to privacy-preserving representation learning methods that consider gender information as a sensitive attribute to protect.

Generating gender-ambiguous voices for privacy-preserving speech recognition

In this article, we discuss the threat to privacy that this passive data collection creates, along with opportunities to mitigate this risk. Furthermore, we argue that the use case of BWCs at work will stimulate the development of solutions that prevent the collection of data that could infringe upon the privacy of the wearer. Finally, we discuss the desirable properties of privacy-enhancing technologies (PETs) for BWC

/pdf/privacy-as-a-feature-for-body-worn-cameras-in-the-spotlight-2vpmxtvy94.pdf

Privacy as a Feature for Body-Worn Cameras [In the Spotlight]

We present an approach for performance evaluation of deterministic video trackers without ground-truth data. The proposed approach detects if a tracker is correctly operating over time using two main steps. First, it transforms the output of the localization step into a distribution of the target state, which emulates a multi-hypothesis tracker. Then, the uncertainty of such distribution is estimated to determine the time instants when the tracker is stable. A time-reversed analysis is used to identify tracker recovery after unsuccessful operation. The proposed approach is demonstrated on the well-known MeanShift tracker. The results over a heterogeneous dataset show that the proposed approach outperforms the related state-of-the-art methods in presence of tracking challenges such as occlusions, illumination and scale changes, and clutter.

/pdf/standalone-evaluation-of-deterministic-video-tracking-17j1ff2ryj.pdf

Andrea Cavallaro

Papers

Video Analytics for Audience Measurement

Recognizing Interactions in Video

Generating gender-ambiguous voices for privacy-preserving speech recognition

Privacy as a Feature for Body-Worn Cameras [In the Spotlight]

Standalone evaluation of deterministic video tracking